[ { "text": "Barack Obama visited Paris.", "tokens": [ "Barack", "Obama", "visited", "Paris", "." ] }, { "text": "Apple Inc. is worth $2.5 trillion.", "tokens": [ "Apple", "Inc.", "is", "worth", "$", "2.5", "trillion", "." ] }, { "text": "I can't believe it's not butter!", "tokens": [ "I", "ca", "n't", "believe", "it", "'s", "not", "butter", "!" ] }, { "text": "Dr. Smith's office (room 42) is closed.", "tokens": [ "Dr.", "Smith", "'s", "office", "(", "room", "42", ")", "is", "closed", "." ] }, { "text": "U.S.A. and U.K. are allies.", "tokens": [ "U.S.A.", "and", "U.K.", "are", "allies", "." ] }, { "text": "They're going to the store.", "tokens": [ "They", "'re", "going", "to", "the", "store", "." ] }, { "text": "He said \"hello\" and left.", "tokens": [ "He", "said", "\"", "hello", "\"", "and", "left", "." ] }, { "text": "The cost is $500.00/month.", "tokens": [ "The", "cost", "is", "$", "500.00", "/", "month", "." ] }, { "text": "New York-based company", "tokens": [ "New", "York", "-", "based", "company" ] }, { "text": "e-mail: test@example.com", "tokens": [ "e", "-", "mail", ":", "test@example.com" ] }, { "text": "10,000 people", "tokens": [ "10,000", "people" ] }, { "text": "3.14159 is pi", "tokens": [ "3.14159", "is", "pi" ] }, { "text": "state-of-the-art technology", "tokens": [ "state", "-", "of", "-", "the", "-", "art", "technology" ] }, { "text": "Mr. and Mrs. Jones", "tokens": [ "Mr.", "and", "Mrs.", "Jones" ] }, { "text": "it's 5:30pm", "tokens": [ "it", "'s", "5:30pm" ] } ]